{
  "abstract": "Clinical AI systems can produce different recommendations when a patient’s race, income, housing status, or gender identity changes, but a differential alone does not establish unjustified bias. What separates a clinically justified differential from an unjustified one is not its size or direction but its origin: whether the feature acts through a clinically justified pathway, or marks how patients of that group have been treated. That distinction is causal, and a model trained only to detect statistical association records that a feature carries information but never why. Existing evidence does not establish reliable recovery of this adjudication inside that model; we therefore argue for explicit causal and normative supervision, whether supplied by an external layer, built into training, or both. We set out a six-criterion rubric, four approaches to implementing it, and a two-sided evaluation reporting preserved clinical sensitivity alongside reduced bias.",
  "abstract_shown": true,
  "affiliations": [
    "BRIDGE GenAI Lab, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, United States of America",
    "Department of Neurology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, United States of America",
    "The Windreich Department of Artificial Intelligence and Human Health, Mount Sinai Medical Center, New York, New York, United States of America",
    "The Hasso Plattner Institute for Digital Health at Mount Sinai, Mount Sinai Health System, New York, New York, United States of America",
    "Department of Radiology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, United States of America"
  ],
  "article_type": "Opinion",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Alon Gorenshtein"
    },
    {
      "affs": [
        1
      ],
      "name": "Mahmud Omar"
    },
    {
      "affs": [
        2
      ],
      "name": "Yiftach Barash"
    },
    {
      "affs": [
        3
      ],
      "name": "Girish N. Nadkarni"
    },
    {
      "affs": [
        4
      ],
      "name": "Eyal Klang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4trazne8a4hr3.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pdig.0001819",
  "fulltext_url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001819",
  "id": "4trazne8a4hr3",
  "issns": [
    "2767-3170"
  ],
  "landing_url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001819",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1702|Ethics and Social Impacts of AI"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Behavior/Human sexual behavior"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Gender identity"
    ],
    [
      "plos",
      "/Medicine and health sciences/Clinical genetics/Genetic diseases/Autosomal recessive diseases/Sickle cell disease"
    ],
    [
      "plos",
      "/Medicine and health sciences/Clinical medicine/Signs and symptoms/Pain"
    ],
    [
      "plos",
      "/Medicine and health sciences/Epidemiology"
    ],
    [
      "plos",
      "/Medicine and health sciences/Epidemiology/Medical risk factors"
    ],
    [
      "plos",
      "/Medicine and health sciences/Hematology/Hemoglobinopathies/Sickle cell disease"
    ],
    [
      "plos",
      "/Medicine and health sciences/Medical conditions/Genetic diseases/Autosomal recessive diseases/Sickle cell disease"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Behavior/Human sexual behavior"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Gender identity"
    ],
    [
      "plos",
      "/Social sciences/Sociology/Social discrimination"
    ]
  ],
  "openalex": "W7225397552",
  "pdf_url": "https://journals.plos.org/digitalhealth/article/file?id=10.1371/journal.pdig.0001819&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-06",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/4trazne8a4hr3.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T12:20:24Z",
      "native_id": "10.1371/journal.pdig.0001819",
      "source": "plos",
      "url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001819"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    },
    {
      "field": "medicine",
      "origin": "plos:epidemiology",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Context is all you need: A causal framework for governing bias in clinical AI",
  "title_text": "Context is all you need: A causal framework for governing bias in clinical AI",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T12:20:48Z",
  "url": "https://research.draconitic.com/paper/4trazne8a4hr3",
  "venue": "PLOS Digital Health",
  "versions": []
}